In CJangelo/COA34: Psychometric Analyses Aligned with FDA COA Guidances 3 and 4

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

Functions to Compute Item Response Distributions

The purpose of this is to show some basic functionality using base R functions. Additional illustrations are available here: https://cjangelo.github.io/R2Word/articles/introduction.html

These sources are common tables that are rendered as output.

A much more sophisticated collection of functions and examples is available in the gtsummary R package.

print.dir = "C:/Users/ciaconangelo/OneDrive - OPEN Health/Documents/misc_R_table_output"

Required R packages

library(COA34)
library(R2Word)

Generate data

  set.seed(12162021)

  sim.out <- COA34::sim_pro_dat_v2(N=1000,
                            number.timepoints = 3,
                            Beta.PRO = NULL,
                            number.of.anchor.groups = 5,
                            polychor.value = 0.7,
                            corr = 'ar1',
                            cor.value = 0.8,
                            #var.values = c(7.136))
                            var.values = c(2))
  dat <- sim.out$dat

Implement drop-out

dat <- COA34::dropout(dat = dat,
               type_dropout  = c('mcar', 'mar', 'mnar'),
               prop.miss = 0.5,
               stochastic.component = 0.2)

Simulate Items

 # Simulate IRT items
 # use the scores generated as the theta in the IRT model 
  sim.out2 <- COA34::sim_irt_item(dat = dat, J = 5, K = 4, latent.variable = 'Y_comp')
    str(sim.out2)
    dat <- sim.out2$dat

# Score the PRO - just take a simple sum score here:
  dat$PRO.score <- apply(dat[, grep('Item', colnames(dat))], 1, sum)

# Create the same PRO score, but with MAR drop-out:
  dat$PRO.score_mar <- dat$PRO.score
  dat$PRO.score_mar[is.na(dat$Y_mar)] <- NA
# Note that you've just set the PRO score to missing wherever the Y_mar variable is missing

# Now for the other missing types:
    dat$PRO.score_mcar <- dat$PRO.score_mnar <- dat$PRO.score
    dat$PRO.score_mcar[is.na(dat$Y_mcar)] <- NA
    dat$PRO.score_mnar[is.na(dat$Y_mnar)] <- NA

  aggregate(cbind(PRO.score, PRO.score_mcar, PRO.score_mar, PRO.score_mnar) ~ Time,
                  function(x) mean(x, na.rm = T), 
                  data = dat, 
                  na.action = na.pass)

Examples

Two useful base R functions (actually in stats package) are aggregate() and xtabs().

Item Response Distributions:

out1 <- do.call(data.frame, stats::aggregate(PRO.score_mar ~ Time,
        FUN = function(x) c(sum(!is.na(x)),
                            mean(x, na.rm = T),
                            sd(x, na.rm = T),
                            quantile(x, na.rm = T)),
        data = dat, na.action = na.pass))
# note: be careful of NA handling
colnames(out1) <- c('Time', 'N', 'Mean', 'SD', '0%', '25%', '50%', '75%', '100%')

R2Word::dump_df_mat_to_file(out = out1,
                            decimals = c(0, 2, 3, 2, 2, 2, 2, 2), 
                            table.title = 'Item Response Distribution - Vignette Illustration', 
                            table.footnote = '**All data simulated',
                            file.name = 'ird1', 
                            print.dir = print.dir)

Cross-Tabs:

out2 <- stats::xtabs( ~  PGIS_delta + Time, data = dat)
out2 <- addmargins(out2, margin = 1)
df <- as.data.frame.matrix(out2)
df <- cbind.data.frame('PGIS_delta' = rownames(out2), df)

R2Word::dump_df_mat_to_file(out = df,
                            decimals = 0,
                            table.title = 'Cross-Table, Vignette Illustration',
                            table.footnote = '**All data simulated',
                            file.name = 'ct',
                            print.dir = print.dir)

If you're using a loop, use as.formula() with paste0():

x <- 'PGIS_delta'
y <- 'Time'
stats::xtabs( as.formula(paste0('~ ',  x, ' + ', y)), data = dat)

More examples...

Additional examples available here: https://cjangelo.github.io/R2Word/articles/introduction.html

A great library: library(dplyr). Example:

library(dplyr)
dplyr::count(dat, Time, PGIS_bl, PGIS_delta, .drop = F)

CJangelo/COA34 documentation built on June 23, 2022, 12:10 p.m.